From 59e7517747f4af3780b3366e7fdb1661aa219795 Mon Sep 17 00:00:00 2001
From: Emi Griffith <me@emigriffith.dev>
Date: Wed, 22 Jul 2026 15:48:23 -0700
Subject: [PATCH] deploy.sh: incoming image tag wins over .image-tags.env;
 health via container healthcheck

Two bugs surfaced wiring dev auto-deploy:
1. Sourcing .image-tags.env clobbered the caller's incoming *_IMAGE_TAG. The
   first backend-only deploy persists FRONTEND_IMAGE_TAG=local (sibling unknown);
   the next frontend deploy then sourced that and pulled :local -> 'manifest
   unknown'. Now the incoming env is captured before sourcing and re-applied.
2. Health-checked services via a host-port curl, but the dev overlay leaves the
   frontend port unpublished (reached via the backend proxy) -> false failure.
   Now polls each container's own HEALTHCHECK status via docker inspect.
---
 deploy/deploy.sh | 34 ++++++++++++++++++++++++----------
 1 file changed, 24 insertions(+), 10 deletions(-)

diff --git a/deploy/deploy.sh b/deploy/deploy.sh
index 6580ec3..87295b1 100755
--- a/deploy/deploy.sh
+++ b/deploy/deploy.sh
@@ -114,9 +114,19 @@ export REGISTRY_HOST BACKEND_IMAGE_PATH FRONTEND_IMAGE_PATH
 # service being deployed then overrides its line below. This file is untracked
 # (see .gitignore), so `git reset --hard` above leaves it in place.
 TAGS_FILE="$APP_DIR/deploy/.image-tags.env"
+# Capture the tags the caller explicitly passed BEFORE sourcing -- they must
+# WIN. The file only supplies the *sibling's* last-known tag; sourcing it
+# unconditionally would clobber an incoming tag (e.g. a frontend deploy whose
+# FRONTEND_IMAGE_TAG got overwritten by the stale `local` the first backend-only
+# deploy persisted for the not-yet-known sibling -> pull `:local` -> "manifest
+# unknown"). So source for the sibling, then re-apply the caller's own value.
+_incoming_backend="${BACKEND_IMAGE_TAG:-}"
+_incoming_frontend="${FRONTEND_IMAGE_TAG:-}"
 if [ -f "$TAGS_FILE" ]; then
   set -a; . "$TAGS_FILE"; set +a
 fi
+[ -n "$_incoming_backend" ] && BACKEND_IMAGE_TAG="$_incoming_backend"
+[ -n "$_incoming_frontend" ] && FRONTEND_IMAGE_TAG="$_incoming_frontend"
 
 # Guard: the service(s) being rolled MUST have a concrete tag supplied now (the
 # sibling's may come from the persisted file). `all` needs both.
@@ -207,21 +217,25 @@ EOF
 # Health check the service(s) we rolled: backend on 8137, frontend on 8080.
 # (For `all`, backend's `/` serving is the readiness signal the old script used
 # and the frontend depends_on backend anyway.)
-declare -A HEALTH_PORTS=( [backend]=8137 [frontend]=8080 )
+# Health via each container's own HEALTHCHECK (docker inspect), NOT a host-port
+# curl: the dev overlay leaves the frontend port UNpublished (reached through the
+# backend's _proxy_to_frontend), so a localhost:8080 curl spuriously fails there.
+# Both images HEALTHCHECK-curl /healthz internally, so this works published or not.
 health_ok=1
 for svc in "${TARGETS[@]}"; do
-  port="${HEALTH_PORTS[$svc]}"
-  url="http://127.0.0.1:${port}/healthz"
-  echo "==> Health check: $svc ($url)"
-  ok=0
-  for i in $(seq 1 30); do
-    if curl -fsS -o /dev/null "$url"; then ok=1; break; fi
-    sleep 1
+  cid=$(docker compose ps -q "$svc" 2>/dev/null)
+  echo "==> Health check: $svc (container health)"
+  ok=0; st=unknown
+  for i in $(seq 1 40); do
+    st=$(docker inspect --format '{{if .State.Health}}{{.State.Health.Status}}{{else}}none{{end}}' "$cid" 2>/dev/null || echo gone)
+    [ "$st" = healthy ] && { ok=1; break; }
+    if [ "$st" = none ] && [ "$(docker inspect --format '{{.State.Status}}' "$cid" 2>/dev/null)" = running ]; then ok=1; break; fi
+    sleep 2
   done
   if [ "$ok" = 1 ]; then
-    echo "==> OK: $svc is serving"
+    echo "==> OK: $svc is healthy"
   else
-    echo "!! Health check failed for $svc ($url)" >&2
+    echo "!! Health check failed for $svc (status=$st)" >&2
     health_ok=0
   fi
 done